Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3160 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1299. Min Act: -0.0002

Data Index: 475250 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1010937 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1126. Min Act: -0.0002

Data Index: 656629 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1558937 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1180724 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1257249 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1177798 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1450400 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1103. Min Act: -0.0002

Data Index: 145521 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1101. Min Act: -0.0003

Data Index: 667369 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1107. Min Act: -0.0003

Data Index: 11472 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1178302 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1082. Min Act: -0.0002

Data Index: 519616 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1318669 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1294750 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1042334 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1650409 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1446207 (Python Code)

Max Activating Token Index: 771

Text #18

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1086. Min Act: -0.0002

Data Index: 189040 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.1299. Min Range: -0.1299

Max Act: 0.1077. Min Act: -0.0002

Data Index: 566264 (C4 (Web Text))

Max Activating Token Index: 261